Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network

Mangalagiri, Jayalakshmi; Chapman, David; Gangopadhyay, Aryya; Yesha, Yaacov; Galita, Joshua; Menon, Sumeet; Yesha, Yelena; Saboury, Babak; Morris, Michael; Nguyen, Phuong

doi:10.1109/csci51800.2020.00160

Cited by 11 publications

(15 citation statements)

References 9 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the diagnosis of COVID-19 using medical imaging has been a priority since the pandemic started, 39 (68%) of 57 studies reported the diagnosis of COVID-19 as the main focus of their work [ 19 - 21 , 23 - 33 , 35 - 37 , 39 , 41 , 42 , 44 , 46 , 50 , 52 , 53 , 55 , 56 , 58 - 60 , 63 - 69 , 71 , 72 ]. In addition, 9 (16%) studies reported data augmentation as the main task addressed in the work [ 18 , 43 , 45 , 49 , 54 , 61 , 62 ], 1 (2%) study reported prognosis of COVID-19 [ 22 ], 3 (5%) studies reported segmentation of lungs [ 34 , 51 , 57 ], and 1 (2%) study reported diagnosis of multiple lung diseases [ 47 ].…”

Section: Resultsmentioning

confidence: 99%

“…In addition, 3 (5%) studies used GANs for segmentation of the lung region within the chest radiology images [ 37 , 51 , 57 ], 3 (5%) studies used GANs for superresolution to improve the quality of the images before using them for diagnosis purposes [ 30 , 44 , 68 ], 5 (9%) studies used GANs for the diagnosis of COVID-19 [ 20 , 58 , 69 , 70 , 72 ], 2 (4%) studies used GANs for feature extraction from images [ 19 , 47 ], and 1 (2%) study used a GAN-based method for prognosis of COVID-19 [ 22 ]. The prevalent mode of imaging is the use of 2D imaging data, and 1 (2%) study reported a GAN-based method for synthesizing 3D data [ 49 ]. Figure 3 (see [ 18 - 74 ]) shows the mapping of the applications of GAN-based methods for all the included studies.…”

Section: Resultsmentioning

confidence: 99%

“…Specifically, the use of X-ray images dominated the studies. In total, 29 (51%) studies used X-ray images of lungs [ 20 , 21 , 25 , 27 - 29 , 31 , 32 , 35 , 37 , 40 - 43 , 45 , 50 , 52 , 54 , 56 , 57 , 59 , 60 , 62 , 64 , 65 , 67 , 70 , 73 , 74 ], while 21 (37%) studies used CT images [ 18 , 19 , 22 - 24 , 26 , 30 , 33 , 34 , 36 , 38 , 48 , 49 , 51 , 53 , 55 , 58 , 61 , 63 , 66 , 71 ], and 6 (11%) studies reported the use of both X-ray and CT images [ 39 , 44 , 46 , 47 , 68 , 72 ]. Only 1 (2%) study used ultrasound images for COVID-19 diagnosis [ 69 ], which shows that ultrasound is not a popular imaging modality for training GANs and other deep learning models for COVID-19 detection (also see Figure 4 ).…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

Ali¹,

Shah²

2022

JMIR Med Inform

View full text Add to dashboard Cite

Background Research on the diagnosis of COVID-19 using lung images is limited by the scarcity of imaging data. Generative adversarial networks (GANs) are popular for synthesis and data augmentation. GANs have been explored for data augmentation to enhance the performance of artificial intelligence (AI) methods for the diagnosis of COVID-19 within lung computed tomography (CT) and X-ray images. However, the role of GANs in overcoming data scarcity for COVID-19 is not well understood. Objective This review presents a comprehensive study on the role of GANs in addressing the challenges related to COVID-19 data scarcity and diagnosis. It is the first review that summarizes different GAN methods and lung imaging data sets for COVID-19. It attempts to answer the questions related to applications of GANs, popular GAN architectures, frequently used image modalities, and the availability of source code. Methods A search was conducted on 5 databases, namely PubMed, IEEEXplore, Association for Computing Machinery (ACM) Digital Library, Scopus, and Google Scholar. The search was conducted from October 11-13, 2021. The search was conducted using intervention keywords, such as “generative adversarial networks” and “GANs,” and application keywords, such as “COVID-19” and “coronavirus.” The review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines for systematic and scoping reviews. Only those studies were included that reported GAN-based methods for analyzing chest X-ray images, chest CT images, and chest ultrasound images. Any studies that used deep learning methods but did not use GANs were excluded. No restrictions were imposed on the country of publication, study design, or outcomes. Only those studies that were in English and were published from 2020 to 2022 were included. No studies before 2020 were included. Results This review included 57 full-text studies that reported the use of GANs for different applications in COVID-19 lung imaging data. Most of the studies (n=42, 74%) used GANs for data augmentation to enhance the performance of AI techniques for COVID-19 diagnosis. Other popular applications of GANs were segmentation of lungs and superresolution of lung images. The cycleGAN and the conditional GAN were the most commonly used architectures, used in 9 studies each. In addition, 29 (51%) studies used chest X-ray images, while 21 (37%) studies used CT images for the training of GANs. For the majority of the studies (n=47, 82%), the experiments were conducted and results were reported using publicly available data. A secondary evaluation of the results by radiologists/clinicians was reported by only 2 (4%) studies. Conclusions Studies have shown that GANs have great potential to address the data scarcity challenge for lung images in COVID-19. Data synthesized with GANs have been helpful to i...

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

Ali¹,

Shah²

2022

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…There have been a number of related works that have investigated the use of GANs to improve the performance of COVID-19 screening from CT scans with reduced training volumes. However, to the best of our knowledge, all recent studies have made use of hundreds of positive cases for training [15], [16], [17], [19], [20]. Hundreds of cases, although small by deep learning standards, is still a substantial training volume to obtain during a pandemic, and the intent of CCS-GAN is to determine how advanced methods may be able to greatly reduce the number of positive images needed for potential future events.…”

Section: Related Workmentioning

confidence: 99%

“…Li et al [19] extended these approaches by combining GANs with ensemble learning and attention mechanisms. Mangalagiri et al also proposed an algorithm for generating 3D diagnostic quality COVID-19 CT scans with a conditional GAN architecture [20]. This method mainly focused on generating the entire CT volume through subdivision into blocks and focusing on blockwise synthesis rather than slice-wise synthesis.…”

Section: Related Workmentioning

confidence: 99%

CCS-GAN: COVID-19 CT-scan classification with very few positive training images

Menon¹,

Mangalagiri²,

Josh³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present a novel algorithm that is able to classify COVID-19 pneumonia from CT Scan slices using a very small sample of training images exhibiting COVID-19 pneumonia in tandem with a larger number of normal images. This algorithm is able to achieve high classification accuracy using as few as 10 positive training slices (from 10 positive cases), which to the best of our knowledge is one order of magnitude fewer than the next closest published work at the time of writing. Deep learning with extremely small positive training volumes is a very difficult problem and has been an important topic during the COVID-19 pandemic, because for quite some time it was difficult to obtain large volumes of COVID-19 positive images for training. Algorithms that can learn to screen for diseases using few examples are an important area of research. We present the Cycle Consistent Segmentation Generative Adversarial Network (CCS-GAN). CCS-GAN combines style transfer with pulmonary segmentation and relevant transfer learning from negative images in order to create a larger volume of synthetic positive images for the purposes of improving diagnostic classification performance. The performance of a VGG-19 classifier plus CCS-GAN was trained using a small sample of positive image slices ranging from at most 50 down to as few as 10 COVID-19 positive CT-scan images. CCS-GAN achieves high accuracy with few positive images and thereby greatly reduces the barrier of acquiring large training volumes in order to train a diagnostic classifier for COVID-19.

show abstract

Generating Scoliotic Computed Tomography Volumes from Finite Element Spine Models

Tapp

Polanco

Kumi

et al. 2022

Computational Biomechanics for Medicine

View full text Add to dashboard Cite

Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network

Cited by 11 publications

References 9 publications

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

CCS-GAN: COVID-19 CT-scan classification with very few positive training images

Generating Scoliotic Computed Tomography Volumes from Finite Element Spine Models

Contact Info

Product

Resources

About